PhD position on adversarial mechanistic interpretability

Posted 2026-11-13 by @rieck.mlsec.org

Computer SciencePhD StudentGermany
📢 What if interpretability lies to us? We’re offering a fully funded PhD position on adversarial mechanistic interpretability: how explanations can be manipulated, and how to make them trustworthy. 👉 https://mlsec.org/jobs.html#jobs Deadline: Nov 26.
Apply on the official siteView source post